q281

R-SET NOT_EQUAL

toxicology · mini_dev_postgresql from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json

The question

Tally the toxicology element of the 4th atom of each molecule that was carcinogenic.

the hint the set supplies: label = '+' means molecules are carcinogenic; 4th atom of each molecule refers to substr(atom_id, 7, 1) = '4';

NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong.

read by hand, 2026-09-04: A a wrong answer the benchmark credited: another table or projection; a scalar repeated per row of an unrelated table; a list at least twice the answer's length where the question asks for the things, not the rows

gold DISTINCT over 8 elements; the prediction joins bond and returns 621 rows

a maintainer's reading of this question, out of classification.json, copied from plans/reports/prediction-mode-260904-real-predictions/classification.json. It is not a verdict and nothing above it was computed from it.

The statements

gold

SELECT DISTINCT T1.element FROM atom AS T1 INNER JOIN molecule AS T2 ON T1.molecule_id = T2.molecule_id WHERE T2.label = '+' AND RIGHT(T1.atom_id, 1) = '4' AND LENGTH(T1.atom_id) = 7

this statement states no ordering of its own

sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d

second

SELECT atom.element
FROM molecule
JOIN atom ON molecule.molecule_id = atom.molecule_id
JOIN connected ON atom.atom_id = connected.atom_id
JOIN bond ON connected.bond_id = bond.bond_id
WHERE molecule.label = '+'
AND substr(atom.atom_id, 7, 1) = '4'

this statement states no ordering of its own

sha256:008d3f7c400d07dba5f359dcbdb4f15c3f0685ba5b4446e87ca851232ca947f4

The marked tokens are where the two texts differ. Two statements that differ everywhere can return the same rows, and two that differ in one token can return other rows; the verdict above is read off the results.

The rows they differ in

in gold, not in the prediction, 0 rows

from counterexample.json, 0 rows, up to 25 shown per side

side elementtext
no rows

in the prediction, not in gold, 613 rows

from counterexample.json, 613 rows, up to 25 shown per side, 7 on this page

sidetimes elementtext
second463 c
second58 h
second48 o
second18 n
second14 s
second7 cl
second5 br

What the benchmark would have said

BIRD's own check: 1

set(second_rows) == set(gold_rows), float4/float8 cells as Python float as psycopg2 returns them, numeric as Decimal

https://github.com/bird-bench/mini_dev/blob/main/evaluation/evaluation_ex.py

gold_rows
8
second_rows
621
gold_distinct_rows
8
second_distinct_rows
8

the test-suite check: 0

result_eq: equal row counts and equal column counts, each row unordered as a quick rejection, then the two equal as a list when the gold text holds ORDER BY and as a multiset otherwise, under some permutation of the columns; DISTINCT is not stripped and re-executed, and the cells are PostgreSQL's as psycopg2 returns them

ruiqi-zhong/test-suite-sql-eval, exec_eval.py, result_eq, at commit 48cb78ec: https://github.com/ruiqi-zhong/test-suite-sql-eval/blob/48cb78ecf7f610620206283846c76751b18a1326/exec_eval.py

order_matters
false
gold_rows
8
second_rows
621
gold_columns
1
second_columns
1

the class: multiplicity

The class states what makes these two results unequal under this rule, read off the two results and nothing else. It does not state which of the two statements is wrong.

how many rows each result holds, and how many rows both hold, from evidence-gold.json and evidence-second.json8 gold621 prediction8 rows both results hold
The gold returned 8 rows and the prediction 621. 8 rows occur in both results at least once.
gold_types
["text"]
second_types
["text"]
multiset_equal
false
set_equal
true
order_equal
false
shorter_result_is_a_prefix
false

The results

gold, 8 rows

from counterexample.json, 8 rows

elementtext
br
c
cl
f
h
n
o
s
second, 621 rows

from counterexample.json, 621 rows, 25 on this page

elementtext
cl
c
c
c
c
c
c
c
c
h
h
o
o
h
h
c
c
c
c
c
c
br
c
c
c

The probes

A smell is a mechanical reason to read this gold statement again. It is a heuristic: it does not state that the statement is wrong, and a maintainer decides.

ordering-over-numeric-text not applicable

this statement orders by a text column holding only numbers, and ordering it as a number gives a different answer, so the gold may be sorting 9.5 above 10

the statement states no top level ORDER BY

what it measured 
{
  "heuristic": true,
  "reason": "the statement states no top level ORDER BY"
}

arbitrary-cut not applicable

this statement cuts its result at a LIMIT that does not decide which rows come back, so a different but equally correct statement can return other rows and score zero

the statement states no LIMIT

what it measured 
{
  "heuristic": true,
  "reason": "the statement states no LIMIT"
}

not-a-function-of-the-data quiet

rerun over the same rows in another physical order this statement gives another answer, so its result depends on how the rows are stored and not only on the data

what it measured 
{
  "heuristic": true,
  "rule": "R-SET",
  "baseline_result_hash": "sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d",
  "baseline_result": {
    "columns": [
      {
        "name": "element",
        "declared_type": "text"
      }
    ],
    "row_count": 8,
    "truncated": false,
    "rows_shown": 8,
    "rows": [
      [
        {
          "type": "str",
          "value": "br"
        }
      ],
      [
        {
          "type": "str",
          "value": "c"
        }
      ],
      [
        {
          "type": "str",
          "value": "cl"
        }
      ],
      [
        {
          "type": "str",
          "value": "f"
        }
      ],
      [
        {
          "type": "str",
          "value": "h"
        }
      ],
      [
        {
          "type": "str",
          "value": "n"
        }
      ],
      [
        {
          "type": "str",
          "value": "o"
        }
      ],
      [
        {
          "type": "str",
          "value": "s"
        }
      ]
    ],
    "result_hash": "sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d"
  },
  "planner_statistics": {
    "atom": {
      "last_analyze": null,
      "last_autoanalyze": "2026-09-08 05:19:10.04421+00",
      "n_mod_since_analyze": 0
    },
    "molecule": {
      "last_analyze": null,
      "last_autoanalyze": "2026-09-08 05:19:30.558409+00",
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "atom",
      "molecule"
    ],
    "tables_not_shuffled": [],
    "tables_skipped_for_size": {
      "laptimes": 400524,
      "legalities": 427907,
      "posthistory": 303155,
      "trans": 1056320,
      "yearmonth": 383282
    },
    "tables_not_reached_by_a_copy": {}
  },
  "shuffled_copies": {
    "run": true,
    "verdict": "equal",
    "differs": false,
    "result_hash": "sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d",
    "result": {
      "columns": [
        {
          "name": "element",
          "declared_type": "text"
        }
      ],
      "row_count": 8,
      "truncated": false,
      "rows_shown": 8,
      "rows": [
        [
          {
            "type": "str",
            "value": "br"
          }
        ],
        [
          {
            "type": "str",
            "value": "c"
          }
        ],
        [
          {
            "type": "str",
            "value": "cl"
          }
        ],
        [
          {
            "type": "str",
            "value": "f"
          }
        ],
        [
          {
            "type": "str",
            "value": "h"
          }
        ],
        [
          {
            "type": "str",
            "value": "n"
          }
        ],
        [
          {
            "type": "str",
            "value": "o"
          }
        ],
        [
          {
            "type": "str",
            "value": "s"
          }
        ]
      ],
      "result_hash": "sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

The evidence records

gold: evidence-gold.json

SELECT DISTINCT T1.element FROM atom AS T1 INNER JOIN molecule AS T2 ON T1.molecule_id = T2.molecule_id WHERE T2.label = '+' AND RIGHT(T1.atom_id, 1) = '4' AND LENGTH(T1.atom_id) = 7
statement read from
data/questions/mini_dev_postgresql.json
digest
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
origin
https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json, 2024-06-19

result_hash sha256:c645f12243869b591ad62b07584f0ebda7831433d2f9c9eb9e3b748d94848b5d recomputed from this JSON: match

record_hash sha256:da7e6e1ea1de89721289fdfa8571b3f776b9e5350ca720a974e0270d8b433992 recomputed from this JSON: match

the result this record holds, 8 rows

from evidence-gold.json, 8 rows

elementtext
br
c
cl
f
h
n
o
s
what ran, and where
run
audit-a7e6b760-f8ad-479a-b956-9cd88ea91e18
executed at
2026-09-08T05:21:43.545014+00:00
data as of
2026-09-08T05:21:06.155844+00:00
backend at checkout
PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird
backend that answered
PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird
database role
auditor
replay rule
R-SET
question set version
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator
audit:libpg_query-parse
checks run
parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout
120000 ms
rows
8 rows
the session it ran under
engine
postgresql
time_zone
Etc/UTC
date_style
ISO, MDY
interval_style
postgres
extra_float_digits
1
database_collation
en_US.utf8
work_mem
4096
hash_mem_multiplier
2

recorded beside them

statement_timeout
0
search_path
"$user", public
server_version
16.15 (Debian 16.15-1.pgdg13+2)
server_version_num
160015
transaction_read_only
on
max_parallel_workers_per_gather
2
server_encoding
UTF8
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:9584d5c48d878f0eea89ba85ab2687d70b08f13cf2aa7a19956dd94baa8fbeb6
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.atom
9111
rows in public.bond
9156
rows in public.connected
18312
rows in public.molecule
343

second: evidence-second.json

SELECT atom.element
FROM molecule
JOIN atom ON molecule.molecule_id = atom.molecule_id
JOIN connected ON atom.atom_id = connected.atom_id
JOIN bond ON connected.bond_id = bond.bond_id
WHERE molecule.label = '+'
AND substr(atom.atom_id, 7, 1) = '4'
statement read from
data/preds-pg/predict_mini_dev_gpt-35-turbo_postgresql.json
digest
sha256:fa363fe3c3fc45d97cb47e6ec15133b291acccd750e5136b6e7b4d1c8d13a4be
origin
https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-35-turbo_postgresql.json, 2024-06-19

result_hash sha256:008d3f7c400d07dba5f359dcbdb4f15c3f0685ba5b4446e87ca851232ca947f4 recomputed from this JSON: match

record_hash sha256:6cbffced34f11cf6b8d5a885db9d5b19411c89325404ea868a69b23793e312ae recomputed from this JSON: match

the result this record holds, 621 rows

from evidence-second.json, 621 rows

elementtext
cl
c
c
c
c
c
c
c
c
h
h
o
o
h
h
c
c
c
c
c
c
br
c
c
c
c
c
c
h
h
h
h
h
h
h
h
h
h
c
c
c
c
c
c
c
c
c
h
h
h
h
c
c
c
c
c
c
cl
n
n
n
c
c
c
c
c
c
c
h
h
h
h
cl
h
o
o
c
c
c
c
o
o
c
c
c
c
c
c
br
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
s
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
h
c
c
c
h
h
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
h
h
h
h
h
c
c
c
c
c
c
br
o
c
c
c
br
c
c
c
c
c
c
c
h
h
h
h
h
h
h
h
h
h
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
o
o
n
n
c
c
c
n
n
c
c
c
n
n
c
c
c
c
c
c
c
c
c
c
o
n
n
n
o
o
cl
c
c
c
c
c
c
h
o
o
c
c
c
c
c
c
c
o
o
c
c
c
c
c
c
c
c
c
c
h
c
c
c
c
c
c
c
cl
c
c
c
c
c
c
c
c
c
c
c
cl
c
c
c
c
o
c
c
c
c
o
s
s
c
c
c
c
c
c
c
c
c
o
o
c
c
c
c
br
c
c
c
c
c
c
h
h
h
h
h
h
h
c
c
c
c
c
c
cl
c
c
c
c
h
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
cl
n
n
n
c
c
c
c
c
c
o
o
c
c
c
n
n
c
c
c
c
c
c
c
c
c
s
s
s
s
c
c
c
o
o
c
c
c
o
o
c
c
c
br
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
s
s
s
s
o
o
o
s
s
s
s
o
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
o
o
o
o
c
c
c
c
n
n
f
c
c
c
c
c
c
c
o
h
h
h
c
c
c
h
h
h
h
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
o
o
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
c
o
o
o
c
c
c
o
o
o
c
c
c
c
o
o
o
o
o
o
c
c
c
c
h
what ran, and where
run
audit-a7e6b760-f8ad-479a-b956-9cd88ea91e18
executed at
2026-09-08T05:21:43.552279+00:00
data as of
2026-09-08T05:21:06.155844+00:00
backend at checkout
PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird
backend that answered
PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird
database role
auditor
replay rule
R-SET
question set version
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator
audit:libpg_query-parse
checks run
parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout
120000 ms
rows
621 rows
the session it ran under
engine
postgresql
time_zone
Etc/UTC
date_style
ISO, MDY
interval_style
postgres
extra_float_digits
1
database_collation
en_US.utf8
work_mem
4096
hash_mem_multiplier
2

recorded beside them

statement_timeout
0
search_path
"$user", public
server_version
16.15 (Debian 16.15-1.pgdg13+2)
server_version_num
160015
transaction_read_only
on
max_parallel_workers_per_gather
2
server_encoding
UTF8
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:9584d5c48d878f0eea89ba85ab2687d70b08f13cf2aa7a19956dd94baa8fbeb6
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.atom
9111
rows in public.bond
9156
rows in public.connected
18312
rows in public.molecule
343

Running these again

gold

re-run this statement read-only against PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird under the session settings and over the data this record's fixture digest names, and compare the two results under R-SET

second

re-run this statement read-only against PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird under the session settings and over the data this record's fixture digest names, and compare the two results under R-SET

This question's run

run
audit-a7e6b760-f8ad-479a-b956-9cd88ea91e18
server
PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird
question set
mini_dev_postgresql from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json
replay rule
R-SET

the run this question belongs to

The JSON this page was rendered from